© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11446
    Prev
    Next
    INDEX
    Explanations

    the word "big" and conjunctions

    oai_token-act-pair · gemini-2.0-flash

    Big

    np_max-act · gemini-2.0-flash

    Big

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeText
    -0.75
    CloseOperation
    -0.69
      
    -0.65
    cism
    -0.65
     THAN
    -0.65
    TagHelper
    -0.64
    migrationBuilder
    -0.64
    EditorBrowsable
    -0.64
    ありますが
    -0.64
     Kelley
    -0.63
    POSITIVE LOGITS
     itſelf
    1.35
     houſe
    1.08
    ſelves
    1.05
     Houſe
    1.04
     Anſ
    1.02
     preſent
    1.00
     pleaſure
    1.00
     Reſ
    0.98
    ſelf
    0.97
     Jefus
    0.96
    Activations Density 2.716%

    No Known Activations